Ai Dreams Forum

Member's Experiments & Projects => General Project Discussion => Topic started by: LOCKSUIT on March 12, 2017, 04:12:26 am

Title: Determined and at the core of AI.
Post by: LOCKSUIT on March 12, 2017, 04:12:26 am
Hello machine.

This is my project thread.

The reason no one is more determined to create AI than me is because only I collect information from everywhere and create a precise hierarchy 24/7. After initialization, it only took me 1 year before I discovered the field of AI that is actually well developed. And I instantly noticed it. I instantly noticed the core of AI from my first read. That's how fast my Hierarchy self-corrects me. Now it's been 1.5 years since and I am here to tell you that I have empirical knowledge that I have the core of AI, and ASI! 100% guarantee !

All of my posts on the forum are in separate threads, mine, yours, but this thread is going to try to hold my next posts together so you can to quickly and easily find, follow, and understand all of my work. Anything important I've said elsewhere is on my desktop, so you will hear about it again here. You don't currently have access to my desktop, only my website in replace to make up for it, while this thread is an extension of it. But this thread won't be permanently engraved to my desktop/website since anything new on this thread will be copied to my desktop/website. Currently my website (and this extension thread) is awaiting my recent work, which I really shouldn't show you all of it.

- Immortal Discoveries
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on March 12, 2017, 04:07:35 pm
The information and discoveries I'm getting recently are overwhelming! I don't know what will happen! I keep making discoveries and findings!

Now I realized how our minds create music that we like! If you remember the Language Neural Network I drew for yous, just how it recognizes letters words sentences topics and outputs them in reverse (use duplicate tree for fastest recognizing), it also recognizes music and outputs music as internal input.
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on March 12, 2017, 06:08:26 pm
Just realized without reading this that we can hear *quiet *whistling by low-activation level but time-dependent frequency vibrations like hit hit hit or hit   hit   hit for deep sounds and high pitches and separately the Volume-Level. On top that we have many sound receptors.

Yet more extendable capabilities for AI and their other sensory types.
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on March 13, 2017, 11:25:54 am
This is amazing.

The reason my AI needed a Language Neural Network pattern recognizer isn't just so it can recognize phonemes ~ words (hashed or not), but also because mine can't sum up what you said i.e. sentence/topic for input NOR output language! (or skills!!).



Also amazing.

The Language Neural Network aka HHMM hierarchy tree has phonemes so words can be recognized and words for sentences and sentences for topics and are of what WE say - no wonder it has pattern recognizers for ex "biotechnology" or "hello there". plus what we output. We don't say jar box can ox open lights NOR fjiagoolut op tala. We Have a common language.

The reason we all have different words/sentences/topics is because by the rewards we switch words for other words to say "Go to money" instead of "go to school". Every time we think we create brand-new sentences/words. How? Supervision by rewards. When we internally hear ourselves mentally we see pictures and hear sentences, these select a single image or new sentence you see hear (word by word) next. It appears then that when sentences form new ones and say are no good, the image it matches OR the sentence in the network is a negative image/network sum-up. After all network sum-up lets you output sum-ups to talk/act, while any of the words might all match positive images i.e. AI-stuff - it must be that negative-sum ups are the case?



So:
Network hierarchy sums.
Network is stereotyped language.
Network creates new language by +/- rewards and knows when in the wrong only by itself.

Examples
"Hello me", "really, well ok"
"why I write standardized words/sentences", "cus I can ask mom for food/etc"
"this sums it up good, I never had these sentences before today, new findings"

As we write sentences, we also stare a lot, and sculpt it better instead of writing it instantly.



Reason I came across this is because I was trying to figure out if we layered sounds for music or line them up. Layering would be realistic (like music production programs) and better therefore. (edit: I wrote "before" instead of "better". . .holy)

The music it creates is what we HEAR on Earth PLUS what we love!!!!!!!!!!!! That's why I write English words ex. "hello, nuggets", and that's why I write *what I write "AI is important". !!!!!!!!!!!!!!!!!!!!!!!!!!!

So when we hear music, we may be able to separate sounds plus re-construct them since won't be complete, so we CAN get them. . .

Now the network has to work multi-time ! It could layer 88 sounds for rendering the piece (not 1 phoneme, the *phonemes will make up the rendering of 88 different instruments/sounds).

If it can line them up, it can do the same for which stacks to line up, and, as for the stacks themselves, if it can use 1 sound/phoneme, why not many you were listening to, enjoyed, and that got separated and re-built.

That's it. We might not even have that ability.
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on March 13, 2017, 12:56:30 pm
What do you think of a program trying every possible particle arrangement to discover all possible technologies waha!?

Or trying all possible circuit arrangements on a neuro-morphic chip that acts like the brain (they exist)?

Plus Evolutionary Algorithms on the computer (clone animal each with mutations and then clone the one that gets the reward function).

Plus my discovery - with 3D-ized objects (yes, we already can), re-arrange them scale them morph them clone them etc until looks like image/data, then do so again in this bounded area, repeat. Until pencil is perfectly straight (or slanted) in ex. flower pot.

Imagine a very large space. The tweaking looks for new technology/AI/AI-improvements in a very small area. You can try farther out. You can try everywhere randomly to see all "fields". Then find what field blooms. Then Evolutionary Algorithms. Then try all possible particle/circuit arrangements from quickest to lengthiest on supercomputers!



We could use this Language NN to control the Auto-Creator within an Evolutionary Algorithm combined with trying every possible neural/atomic configuration to find AI, technologies, knowledge.

The LNN could also be used for recognizing/remembering vision/actions, recognizing/building technologies/knowledge. So could the Auto-Creator, E.A., and trying all possibilities.

First use Auto-creator/arranger to create something similar ex. recognize 2 human attributes/start from noise and creates model that has both within Evolutionary Algorithm, then try all possible neural/particle configurations to 100% for sure find AI
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on March 15, 2017, 06:15:03 am
New thread I posted on chatbots:
http://aidreams.co.uk/forum/index.php?topic=12033.msg46022;topicseen#new (http://aidreams.co.uk/forum/index.php?topic=12033.msg46022;topicseen#new)
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on March 18, 2017, 03:37:41 pm
GENERATING A BRAIN
http://aidreams.co.uk/forum/index.php?topic=12039.msg46065#msg46065 (http://aidreams.co.uk/forum/index.php?topic=12039.msg46065#msg46065)

Why Automation is incredible.
http://aidreams.co.uk/forum/index.php?topic=12040.msg46076#msg46076 (http://aidreams.co.uk/forum/index.php?topic=12040.msg46076#msg46076)

3D creating:
http://aidreams.co.uk/forum/index.php?topic=11451.msg46112#msg46112 (http://aidreams.co.uk/forum/index.php?topic=11451.msg46112#msg46112)

How do the quad/spider robots learn to crawl?
http://aidreams.co.uk/forum/index.php?topic=12066.msg46209;topicseen#new (http://aidreams.co.uk/forum/index.php?topic=12066.msg46209;topicseen#new)
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on April 01, 2017, 03:33:26 am
ALL MY TEXT KNOWLEDGE/WORK. . . . . . . . . . . . !

http://advancessss.deviantart.com/art/The-Everything-672200028?ga_submit_new=10%3A1491013451&ga_type=edit&ga_changes=1&ga_recent=1 (http://advancessss.deviantart.com/art/The-Everything-672200028?ga_submit_new=10%3A1491013451&ga_type=edit&ga_changes=1&ga_recent=1)

DAT BIG DADA!

......OK SO THAT'S NOT ALLLL MY TEXT BUT ITS LIKE, MOST OF IT
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on April 02, 2017, 03:35:28 am
Vestibulo–Ocular Reflex - a key to human intelligence.
http://aidreams.co.uk/forum/index.php?topic=12075.msg46271#msg46271 (http://aidreams.co.uk/forum/index.php?topic=12075.msg46271#msg46271)

Dreams.
http://aidreams.co.uk/forum/index.php?topic=12201.msg46797#msg46797 (http://aidreams.co.uk/forum/index.php?topic=12201.msg46797#msg46797)
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on June 02, 2017, 11:41:22 pm
Tip of the day:


- There is ways to Generate ex. bits/pixels/3D-objects and ways for those ex. clone/scale 3D-objects, including using pre-made assets.

- There is ways to Discriminate.
Title: Re: Determined and at the core of AI.
Post by: Art on June 03, 2017, 05:39:25 pm
are
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on June 16, 2017, 08:18:20 am
Old thread replied to.
http://aidreams.co.uk/forum/index.php?topic=9147.msg46910;topicseen#new
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on June 18, 2017, 01:15:06 pm
MY MILLION DOLLAR BABY

link removed
Title: Re: Determined and at the core of AI.
Post by: korrelan on June 18, 2017, 04:22:30 pm
I hope Mac'y Deez is paying you handsomely for the advertising... lol.

Mmmm... Chicken fat wrapped in faux breadcrumbs...

 :)
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on June 18, 2017, 06:14:39 pm
That absolutely makes no sense.
Title: Re: Determined and at the core of AI.
Post by: korrelan on June 18, 2017, 06:24:46 pm
It might be a local colloquialism you are not grasping...

The first frame of your video... Yummy...

 :)
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on June 19, 2017, 02:46:00 am
Yeh ok. Everything after the 1st frame doesn't matter.
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on June 19, 2017, 01:52:53 pm
I can actually create Lucifer.

And Jesus.

In a virtual simulation inside my computer.

They can actually exist just as would expect. They would be immortal, think as should and have agendas, appear in depth room with saints, sacrificies, resurect Jesus again, have the holy spirit fly out and go into everyone, have magical powers, and live in peace in Their Heaven while Lucifer burns in hell. And damn the evil sinners that die so they awake in hell or heaven.

Is this really a simulation? Anything appears possible! Christianity, AI, somethingElseExample, other physics, anything. Why have one or say this is right when simply all and anything is possible.

Our universe must be the only base, and has a clear algorithm way of what creates life and how they will, enjoy the universe.
Title: Re: Determined and at the core of AI.
Post by: Art on June 19, 2017, 06:02:02 pm
Is this Virtual Simulation that's inside of your computer something that you can share with the rest of us?

I'm sure some of us would like to see it.
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on June 20, 2017, 05:02:44 am
Lolz. Not large enough computer for that.

Did any of yous get the chance to see my latest video of my 3D simulation baby? It was only up for a short time. Korrelan got to flip it on, but he didn't think much of it.
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on June 24, 2017, 08:00:20 am
OH MM G

I just came up with a complete Pattern Recognition solution.

It's the simplest PR you can code, and is super easy to code. It's the most efficient PR in the universe, yes not even billions, but infinite times more efficient than current PRs. And it can detect images that are 100 trillion trillion pixels big. Even 3D PR. And video recognition. And it has perfect recognition with 0 error rate!

I'll give you 2 hints. It only works in simulation. And I call it Identity Recognition.

My human baby will now not only crawl talk etc all without PR, but will now have full access to becoming adult by my new PR technology!

OMG
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on June 24, 2017, 02:36:46 pm
What do yous think about that!?
Title: Re: Determined and at the core of AI.
Post by: korrelan on June 24, 2017, 02:40:41 pm
If true then it sounds amazing... I'll bite...

Tell us more about 'Identity Recognition' the 'most efficient PR in the universe'

 :)
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on June 24, 2017, 03:28:13 pm
It's true. And it works.

I'll tell you *some* more.

Btw I solved it before getting out of bed, before reading your coincidental post that mentions some similar timbits (not that your post really brings it up, only that it mentions timbits on the idea. Only I'd see the timbits now though since realized the idea). Ok... I talk in my head like this all day... OK, ok, ..     moving on

Sure you easily save all pixel images. But you don't have to have a unique image made of all these pixels, struggle to search for the match. You rename all images, and when an "image" enters, it can easily select the matching image.

The idea uses small codes, like 0, 1, 2, 3, or 0, 1, 00, 01. You name all objects in the simulation, faces, angles, local areas ex. dog bowl's circle rim, curve, smaller curve, line, dot, then the walls, water hole, dog bowl global. Then when it sees objects, it "sees" a very small name number.

It saves all these "images" i.e. very small named-by-you numbers/codes, just like PRs do. It has input. Input searches EASY imagine a line from 0 to 3,000, input "77" ex. "door" enters and only has to stop on the 77 mark address. Imagine a train line of 8,000 names (0-8,000 are the names, yes numbers), and when 678 enters, imagine it has 678 amount of juice, and the resistor stops it at 678.

Get it?

Discuss.
Title: Re: Determined and at the core of AI.
Post by: korrelan on June 24, 2017, 04:37:10 pm
Erm... but lets say you have an image of me that you index/ encode as 007 (lol). You can use the 007 as reference representing me in other operations but the system would still have to recognise me when I entered the room, it would still have to go through the whole pattern recognition process to arrive at 007, to recognise me. 

This why we use feature recognition...

01 Object is 6'3"
02 Object has human outline
03 Object has brown hair
04 Object is male

if (01,02,03,07) then object = 002
if (01,02,03,04) then object = 007 <<
if (01,02,03,08) then object = 009

So you are not negating the complex pattern recognition required.

 :)
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on June 24, 2017, 05:09:29 pm
Whahahaha, ahahahaha, you think you have defeated me? Whahaha, look above. No, you have not.

There is no images ever taken/used. You're in a 3D simulation world. You name objects and parts on them. When you "look" at an object, you get a small "image" i.e. small number ex. 24. You can save a million images but each is not a million pixels, only a couple at most :). Efficient, easy, perfect, etc.

You give a coffee cup, korrelan, and the outline of his nose each a unique identity number. You don't need to use a image of a million pixels to have a identity for a coffee cup. Just ex. 24.

If it detects a play or instantly detects multiple "images" parallely even, these can select as a multi-match another sense or actions, since you brought that idea up. The contendees ("images") of the multi-match don't have to be numbered i.e. if 02 & 06 = 003, just linked by tethers, and initiate if matches right guys. But you can call my numbers numbers, oh wait that's pointless. However you can call multi-matches numbers, while having them be/select/link-to say actions. I will note down from you you can number name real camera images, more knowledge.
Title: Re: Determined and at the core of AI.
Post by: korrelan on June 24, 2017, 07:13:37 pm
Oh! You're talking about 'game' programming.

Then yes... we have been using this method for many, many, years and it works. 

Every game you have ever played probably used this schema. 

Unfortunately it can't be converted/ extrapolated to real world situations/ experiences.

But... the idea is still valid... if you can create an AI that can exist with human levels of intelligence, even within a simulated world then you are still onto a winner.  We programmers can get the real world data in there...

 :)
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on June 24, 2017, 07:34:51 pm
So do you understand that, in simulation, without taking pictures with a "virtual camera", I can completely surpass your life's problem of Pattern Recognition, and easily with 0 error recognize everything from faces to walls to noses to lines?

Why not drop the PR part of your project and jump in this boat? It's easy and 0 error rate.
Title: Re: Determined and at the core of AI.
Post by: korrelan on June 24, 2017, 07:50:04 pm
Quote
Why not drop the PR part of your project and jump in this boat? It's easy and 0 error rate.

Because I've been coding simple scenarios like that for donkeys years... there is no recognition required, it's totally useless for an 'real world' AGI.

For it to be viable in the real world your AI would have to exist in simulated world as rich as the real world... with characters as diverse as real humans,,, Nah! sorry lock... won't work for the real world.

 :)
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on June 24, 2017, 09:48:36 pm
In simulation, it will recognize everything in the house, and voice won't be that hard either. It will talk to me. Then after it thinks, it will be ready to come out of simulation.
Title: Re: Determined and at the core of AI.
Post by: korrelan on June 24, 2017, 11:21:37 pm
Quote
Then after it thinks, it will be ready to come out of simulation.

And there it will fail...

The real world does not have simple labels/ indexes for objects or people.

It will have to recognise it's surroundings from its sensory streams, just like humans do.

 :)
Title: Re: Determined and at the core of AI.
Post by: LOCKSUIT on June 24, 2017, 11:40:01 pm
Bro come on. Once it's all like talkin n all in simulation, it''s a devil incarnate. The 1st AI made will be a God on Earth. This thing will guide me the way, break out, learn, anything required. It'll be making a simu heaven tech world in there, getting me to add huge supercomputers, then break out.
Title: Re: Determined and at the core of AI.
Post by: korrelan on June 25, 2017, 12:01:13 am
Nope it won't.

The whole premiss for your idea is to build a human level intellect using short indexes/ codes to represent objects, etc.

IF... I say IF... you did manage to build such a intellect inside a simulation, the indexes wouldn't exist in the real world.

Soz dude... it would fail.

Edit: That is just my humble opinion and I could be wrong.  Guess you will have to write/ build it and find out.

 :)
Title: Re: Determined and at the core of AI.
Post by: Freddy on June 25, 2017, 01:25:34 am
Maybe there is a half way house. I'm thinking about VR/AR - some of the things I have seen for AR combine virtual things with real world things. Part of the process in some AR is to model the room and so on, obstacles etc. Maybe there is some mileage there.